JP2007256618A - Search device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide technology capable of searching a singer who has a desired singing feeling in a karaoke device. <P>SOLUTION: When a CPU 31 of a server unit 3 detects that a singing analysis data is received via a communication section 35, the received singing analysis data is compared with the singing analysis data stored in a singing analysis database storage area 34a, and according to its matching rate, one or more singing analysis data are selected from the singing analysis database storage area 34a. The CPU 31 reads identification information corresponding to the selected singing analysis data from the singing analysis database storing area 34a, and transmits the read identification information to the karaoke device 2 via a communication network 4. A CPU 11 of the karaoke device 2 displays a singer indicated by the received identification information on a display section 15. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a technique for searching for a singer.

In a karaoke apparatus, various methods for scoring the skill of a singer's singing have been proposed. For example, Patent Document 1 proposes a method of determining which part has not been successfully sung by comparing the pitch of the sung voice with a reference pitch. Moreover, in the technique of patent document 2, a singer's song is scored according to the physical characteristics of the song sung by the singer, the listener's evaluation of the song, etc., and the scoring result for better scoring. A method of accumulation has been proposed.
Japanese Patent Application Laid-Open No. 2004-093601 JP 2000-99014 A

  By the way, there are various types of singing performed by a plurality of people such as duet, a cappella, gospel, and chorus. The fact that uniform “sound quality” is effective is apparent from examples such as the twin singer “The Peanuts”, and unlike instrumental ensembles, the singing feeling of a person has a large individual difference in “pitch feeling”. Even advanced choirs have a great deal of difficulty in getting this “pitch” in practice. The sense of pitch here refers to a fine pitch expression that cannot be expressed in the score, such as where the pitch of the singing is raised or lowered, or where the central pitch of the vibrato is placed.

Among users of karaoke devices, search for people who have a similar feeling to singing or who have a certain feeling of singing (for example, people who have the same pitch and different voice quality, etc.) as a duet or chorus. Some people want to do it.
The present invention has been made under the above-described background, and an object of the present invention is to provide a technique by which a user can find a singer having a desired singing feeling.

In order to solve the above-mentioned problems, the present invention provides a storage means storing a plurality of pairs of identification information for identifying a singer and singing analysis data indicating characteristics of the singing voice of the singer, and characteristics of the singing voice of the singer. The singing analysis data indicating the singing analysis data acquired by the acquisition unit and the singing analysis data stored in the storage unit are compared, and the storage unit stores the singing analysis data indicating the degree of coincidence. Selecting means for selecting one or more song analysis data from the song analysis data, and output means for reading identification information corresponding to the song analysis data selected by the selection means from the storage means and outputting the read identification information; A search device is provided.
In a preferred aspect of the present invention, the storage means stores singer information relating to a singer in association with the identification information, and the output means identifies identification information corresponding to the song analysis data selected by the selection means. Is read from the storage means, and the read identification information is output, and the singer information corresponding to the identification information is read from the storage means, and the read singer information is notified.
In another preferable aspect of the present invention, the storage means stores a communication address indicating a contact information of the singer in association with the identification information, and the output means is singing analysis data selected by the selection means. Is read from the storage means, and the read identification information is output, and the communication address corresponding to the identification information is read from the storage means to indicate that it has been selected for the read communication address. It is characterized by communicating a message.
In a further preferred aspect of the present invention, the song analysis data is data indicating at least one of the pitch, spectrum and power of the voice.
In another preferred aspect of the present invention, the singing analysis data is technique data indicating the type and timing of a technique used for singing.
Further, in a further preferred aspect of the present invention, it comprises an input means for outputting the input voice of the singer as voice data, and a generating means for generating the song analysis data from the voice data output by the input means, The acquisition unit acquires singing analysis data generated by the generation unit.
In a further preferred aspect of the present invention, the apparatus further comprises storage control means for storing the song analysis data generated by the generation means in the storage means.

  According to the present invention, a user can find a singer who has a desired singing feeling.

<A: First Embodiment>
<A-1: Configuration>
FIG. 1 is a block diagram showing an example of the overall configuration of a search system 1 according to an embodiment of the present invention. The search system 1 is configured by connecting karaoke devices 2 a, 2 b, 2 c and a server device 3 via a communication network 4. In addition, although three karaoke apparatuses are illustrated in FIG. 1, the number of karaoke apparatuses included in the search system is not limited to three and may be more or less than this. In the following description, when it is not necessary to distinguish the karaoke apparatuses 2a, 2b, and 2c, they are simply referred to as “karaoke apparatus 2”.

  FIG. 2 is a block diagram illustrating a hardware configuration of the karaoke apparatus 2. In the figure, a CPU (Central Processing Unit) 11 reads a computer program stored in a ROM (Read Only Memory) 12 or a storage unit 14, loads it into a RAM (Random Access Memory) 13, and executes it. Control each part of the karaoke apparatus 2. The storage unit 14 is a large-capacity storage unit such as a hard disk, and includes an accompaniment data storage area 14a, a lyrics data storage area 14b, an audio data storage area 14c, and a song analysis data storage area 14d. . The display unit 15 is a liquid crystal display, for example, and displays various screens such as a menu screen for operating the karaoke device 2 and a karaoke screen in which lyrics telop is superimposed on a background image under the control of the CPU 11. The operation unit 16 provides various keys and outputs a signal corresponding to the pressed key to the CPU 11. The microphone 17 is a sound collecting unit that picks up the sound produced by the singer. The sound processing unit 18 converts sound (analog data) collected by the microphone 17 into digital data and supplies the digital data to the CPU 11. The speaker 19 is connected to the sound processing unit 18 and emits sound with an intensity corresponding to a signal output from the sound processing unit 18. The communication unit 20 includes various communication devices and the like, and exchanges data with the server device 3 via the communication network 4 under the control of the CPU 11.

  The accompaniment data storage area 14a of the storage unit 14 is accompaniment data in, for example, MIDI (Musical Instruments Digital Interface) format, and includes the pitch (pitch), strength (velocity), and effects of various musical instruments that accompany each song. Accompaniment data in which information indicating the assignment or the like is described according to the progress of the music is stored. The accompaniment data includes melody data indicating the scale of the melody of the music. The lyrics data storage area 14b stores lyrics data indicating lyrics corresponding to the accompaniment data. In the audio data storage area 14c, audio data A / D converted from the microphone 17 via the audio processing unit 18 is stored in time series, for example, in WAVE format or MP3 (MPEG Audio Layer-3) format. The song analysis data storage area 14d stores song analysis data indicating the characteristics of the singer's voice. In the present embodiment, information indicating the spectrum, pitch, and power of voice data is used as singing analysis data.

  FIG. 3 is a block diagram illustrating a hardware configuration of the server device 3. In the figure, the CPU 31 reads out a computer program stored in the ROM 32 or the storage unit 34, loads it into the RAM 33, and executes it to control each unit of the server device 3. The storage unit 34 is a large-capacity storage unit such as a hard disk, and has a song analysis database storage area 34a and a singer information table storage area 34b. The communication unit 35 includes various communication devices and the like, and exchanges data with the karaoke device 2 via the communication network 4 under the control of the CPU 31.

The song analysis database storage area 34a of the storage unit 34 stores a song analysis database that is a set of song analysis data.
FIG. 4 is a diagram showing an example of the contents of the song analysis database. As shown in the figure, this song analysis database stores a plurality of pairs of “identification information” and “singing analysis data”. Among these items, information for identifying the singer is stored in the “identification information” item. This identification information may be information for identifying an individual singer such as a membership number or a user ID. Or the information which shows the place (room number, store number) and time where singing was performed may be sufficient. In short, this identification information may be any information as long as it identifies the singer.
Next, singing analysis data generated by the karaoke apparatus 2 is stored in the “singing analysis data” item. In this song analysis database, a plurality of song analysis data are stored as shown in the figure.

  Next, in the singer information table storage area 34b of the storage unit 34, “identification information” and “singer information” are stored in association with each other. Information for identifying a singer is stored in the item “identification information”. The item “singer information” stores information about the singer such as the name of the singer and the name of the store used by the singer.

<A-2: Operation>
Next, the operation of the search system 1 will be described.
<A-2-1: Singing analysis data storage operation>
First, the song analysis data storage operation of the search system 1 will be described.
The singer operates the operation unit 16 of the karaoke apparatus 2 to instruct reproduction of accompaniment data. In response to this instruction, the CPU 11 reads the accompaniment data from the accompaniment data storage area 14 a and supplies it to the audio processing unit 18. The sound processing unit 18 converts the supplied accompaniment data into an analog signal and supplies it to the speaker 19 for sound emission. At this time, the CPU 11 may control the display unit 15 to display a message prompting singing such as “Please sing along with the accompaniment”. The singer sings along with the accompaniment emitted from the speaker 19. At this time, the voice of the singer is picked up by the microphone 17, converted into a voice signal, and supplied to the voice processing unit 18. The audio data A / D converted by the audio processing unit 18 is stored in the audio data storage area 14c of the storage unit 14 in time series.

  When the reproduction of the accompaniment data ends, the CPU 11 separates the audio data stored in the audio data storage area 14c into frame units having a predetermined time length, and calculates the pitch, spectrum, and power from the audio data in frame units. The spectrum may be detected by using FFT (Fast Fourier Transform). The CPU 11 stores information indicating the calculated pitch, spectrum, and power as song analysis data in the song analysis data storage area 14d. The song analysis data may be information indicating the pitch, spectrum and power of the entire song, or may be information indicating the pitch, spectrum and power of a part of the song.

  Subsequently, the CPU 11 transmits the generated song analysis data and identification information to the server device 3 via the communication network 4. The identification information may be input by the singer through the operation unit 16 or may be automatically generated by the CPU 11.

  When detecting that the song analysis data has been received via the communication network 4, the CPU 31 of the server device 3 stores the received song analysis data and identification information in the song analysis database storage area 34 a of the storage unit 34.

  The karaoke device 2 generates singing analysis data each time a singer performs a song, and transmits the generated singing analysis data and identification information to the server device 3. Thereby, the server apparatus 3 stores song analysis data for a plurality of songs.

<A-2-2: Search operation>
Next, the search operation of the search system 1 will be described.
First, the user of the search system 1 operates the operation unit 16 to instruct a search. When the CPU 11 of the karaoke apparatus 2 detects that the search is instructed, the singing analysis data generation process described above is performed. That is, the CPU 11 reads the accompaniment data from the accompaniment data storage area 14a, emits the accompaniment sound from the speaker 19, collects the user's voice with the microphone 17, and generates song analysis data from the voice data.
When generating the song analysis data, the CPU 11 of the karaoke device 2 transmits the generated song analysis data to the server device 3 via the communication network 4.

  When the CPU 31 of the server device 3 detects that the song analysis data has been received (acquired) via the communication unit 35, the received song analysis data is compared with the song analysis data stored in the song analysis database storage area 34a. Then, according to the degree of coincidence, one or more song analysis data are selected from the song analysis data stored in the song analysis database storage area 34a. Specifically, for example, the CPU 31 stores the pitch of the received singing analysis data (hereinafter, “reception analysis data”) and the singing analysis data (hereinafter, “memory analysis data”) stored in the singing analysis database storage area 34a. Singing analysis data having the highest degree of coincidence is selected by comparing with the pitch. Similarly, the spectrum of the reception analysis data and the spectrum of the storage analysis data are compared, and the song analysis data having the highest degree of coincidence is selected, and the power of the reception analysis data is compared with the power of the storage analysis data. Then, the singing analysis data having the highest degree of coincidence is selected. In the present embodiment, for each of the pitch, spectrum, and power, the song analysis data having the highest degree of coincidence is selected one by one. However, the number to be selected is not limited to one. Two or more song analysis data may be selected for each of pitch, spectrum, and power.

  The CPU 31 of the server device 3 reads identification information corresponding to the selected song analysis data from the song analysis database storage area 34a, and transmits (outputs) the read identification information to the karaoke device 2 via the communication network 4. At this time, the CPU 31 reads the singer information corresponding to the identification information from the singer information table storage area 34b, and transmits the read singer information together with the identification information.

CPU11 of the karaoke apparatus 2 outputs the received singer information to the display part 15, controls the display part 15, and displays the content which singer information shows on the display part 15. FIG.
FIG. 5 is a diagram illustrating an example of a screen displayed on the display unit 15 of the karaoke apparatus 2. In the example shown in FIG. 5, “Singer A” is displayed as the singer with the highest degree of matching of the pitch, “Singer B” is displayed as the singer with the highest degree of coincidence of the spectrum, An example in which “Singer C” is displayed as the singer with the highest power matching degree is shown.

  As described above, in this embodiment, the singing voice of the singer is analyzed, the singing analysis data as the analysis result is accumulated, and the search result is notified to the user. The user can use the search system 1 to find a person who has a similar singing feeling, such as a sense of pitch, sound quality, dynamics, etc., and who sings who is similar I can know that. Thereby, for example, it is possible to automate the chorus audition and member recruitment. Alternatively, virtual duet, virtual chorus, etc. (remote location) by transmitting audio data can be performed.

<B: Second Embodiment>
Next explained is the second embodiment of the invention. This embodiment is different from the first embodiment described above in that the content of the song analysis data is different. Therefore, in the following description, the same code | symbol is provided about the component similar to 1st Embodiment mentioned above, and the description is abbreviate | omitted.

In the present embodiment, technique data indicating the type and timing of the singing technique used for singing is used as the singing analysis data.
FIG. 6 is a diagram illustrating an example of the content of song analysis data in the present embodiment. As shown in the drawing, in the song analysis data, items of “section information” and “type information” are associated with each other. Among these items, the “section information” item stores information indicating a section in which the singing technique is used in the audio data. The section indicated by the section information may be a section having a time width represented by the start time information and the end time information, or may indicate a certain point of time.

  In the “type information” item, information for identifying a plurality of types of singing techniques set in advance is stored. This “type information” is information for identifying a singing technique such as “vibrato”, “shakuri”, “fist”, “farset”, “tsukkomi”, “for”, “breathing”, and the like. “Vibrato” refers to a technique that raises and lowers the pitch of the sound only slightly and produces a trembling tone. “Shikkuri” refers to a technique in which sound is generated from a sound lower than the target sound, and the pitch is smoothly brought close to the target sound. “Fist” refers to a technique for adding a decorative undulation. “Falset” indicates a technique of singing with a so-called “back voice”. “Tsukumi” refers to a technique for making the singing start earlier than the original timing. “For” indicates a technique for making the singing timing later than the original timing. The “breathing” indicates the timing when the singer breathes.

Next, the song analysis data generation process performed by the karaoke apparatus 2 will be described below.
The singer operates the operation unit 16 of the karaoke apparatus 2 to instruct reproduction of accompaniment data. In response to this instruction, the CPU 11 reads the accompaniment data from the accompaniment data storage area 14 a and supplies it to the audio processing unit 18. The sound processing unit 18 converts the supplied accompaniment data into an analog signal and supplies it to the speaker 19 for sound emission. The singer sings along with the accompaniment emitted from the speaker 19. At this time, the voice of the singer is picked up by the microphone 17, converted into a voice signal, and supplied to the voice processing unit 18. The audio data A / D converted by the audio processing unit 18 is stored in the audio data storage area 14c of the storage unit 14 in time series.

  When the reproduction of the accompaniment data is completed, the CPU 11 performs a sound analysis process on the sound data stored in the sound data storage area 14c, and calculates a pitch, power, and spectrum corresponding to the time from the sound data. Subsequently, the CPU 11 analyzes the melody data included in the accompaniment data stored in the accompaniment data storage area 14a and the voice data stored in the voice data storage area 14c in units of a predetermined frame, Detect the temporal correspondence of.

  Next, the CPU 11 analyzes the pattern of temporal changes in pitch, power, and spectrum calculated from the audio data, determines whether or not this analysis result corresponds to a predetermined pattern, and responds accordingly. In this case, the section corresponding to the pattern is specified as a section in which a specific singing technique is used. Then, the CPU 11 stores the section information of the specified section in the song analysis data storage area 14d of the storage unit 14 in association with the type information indicating the song technique.

  Here, the identification process of the area where each singing technique is used is demonstrated below. In the present embodiment, the CPU 11 specifies (detects) a section in which each singing technique of “vibrato”, “shakuri”, “fist”, “farset”, “tsukkomi”, “for” and “breathing” is used. ) Of these, “vibrato” and “shrimp” are detected based on the pitch calculated from the audio data. “Fist” and “Falset” are detected based on the spectrum calculated from the audio data. Also, “for” and “tsukkomi” are detected based on the pitch and melody data calculated from the audio data. Further, “breathing” is detected based on the power calculated from the voice data and the melody data.

  Based on the correspondence between the audio data and the melody data and the pitch calculated from the audio data, the CPU 11 determines the start time of the sound included in the audio data and the start time of the sound of the melody data corresponding to the sound. Identify different sections. Here, the CPU 11 is a section in which the pitch change timing of the voice data appears earlier than the pitch change timing of the melody data, that is, the start time of the sound included in the voice data corresponds to the sound of the melody data corresponding to the sound. For a section earlier than the start time, this section is specified as a section in which the “Tsukumi” singing technique is used. The CPU 11 stores the section information of the specified section in the song analysis data storage area 14d of the storage unit 14 in association with the identification information indicating “push”.

  Conversely, the CPU 11 shows that the change timing of the pitch of the audio data appears later than the change timing of the pitch of the melody data based on the correspondence between the audio data and the melody data and the pitch calculated from the audio data. That is, a section where the start time of the sound included in the sound data is later than the start time of the sound of the melody data corresponding to the sound, and the section where the singing technique for “for” is used as the detected section To be identified.

  Further, the CPU 11 analyzes the pattern of the temporal change of the pitch calculated from the audio data, detects a section where the pitch continuously fluctuates within a predetermined range above and below the center frequency, and detects it. This section is identified as a section in which the “vibrato” singing technique is used.

  Further, the CPU 11 analyzes the pattern of the temporal change of the pitch calculated from the audio data, detects a section in which the pitch continuously changes from a low pitch to a high pitch, and sings the detected section as a “shrimp” song. Identifies the interval in which the technique is used. This process may be performed based on the correspondence with the melody data. In other words, the CPU 11 may detect a section in which the pitch of the voice data is continuously approaching the pitch of the melody data from a low pitch based on the correspondence relationship between the voice data and the melody data.

  Further, the CPU 11 is a section in which the melody data is voiced based on the correspondence between the voice data and the melody data and the power calculated from the voice data, and the power value of the voice data is higher than a predetermined threshold value. A small section is detected, and the detected part is specified as the "breathing" section.

  Further, the CPU 11 analyzes the temporal change pattern of the spectrum calculated from the audio data, detects a section where the spectral characteristics are abruptly changed to the predetermined change state, and detects the detected section as “ It is specified that the section uses the “Falset” singing technique. Here, the predetermined change state is a state in which the harmonic component of the spectrum characteristic is extremely reduced. For example, as shown in FIG. 7, in the case of a local voice, many harmonic components are included (see FIG. 7A). b)). In this case, the CPU 11 may also refer to whether or not the pitch has changed significantly upward. The falset is sometimes used even when generating the same pitch as the local voice, but is generally a technique used when generating high-pitched sounds that cannot be generated by the local voice. Therefore, “Falset” may be detected only when the pitch of the audio data is equal to or higher than a predetermined pitch. In addition, since the pitch range using the falset is generally different between male voice and female voice, gender detection is performed based on the voice data range and formants detected from the voice data, and based on this result, the pitch range for falset detection is determined. It may be set.

  In addition, the CPU 11 detects a section in which the mode of change of the spectrum characteristic is variously switched in a short time, and identifies the detected part as a part where the “fist” singing technique is used. In the case of “fist”, it is a singing technique that adds a taste that can be changed by changing the voice color and utterance method in a short section, so the spectral characteristics change variously in the section where this technique is used. .

  As described above, the CPU 11 detects the section in which each singing technique is used from the voice data, associates the section information indicating the detected section with the type information indicating the singing technique, and singing analysis data in the storage unit 14. Store in the storage area 14d.

  The CPU 11 of the server device 3 compares the acquired song analysis data with the song analysis data stored in the song analysis database storage area 34a, and selects song analysis data according to the degree of coincidence. Thus, in this embodiment, since the technique data which shows a singing technique are used as song analysis data, the singer who resembles the timing etc. which use a singing technique can be searched.

<C: Modification>
As mentioned above, although embodiment of this invention was described, this invention is not limited to embodiment mentioned above, It can implement with another various form. An example is shown below.
(1) In embodiment mentioned above, CPU31 of the server apparatus 3 was made to select song analysis data with the highest coincidence with the acquired song analysis data. In addition to this, a combination of who and who is similar in a certain group may be generated and notified to the user. Specifically, for example, in two groups of a group of singer A to singer D and a group of singer E to singer H, a combination with a high degree of coincidence of singing analysis data (for example, “singer” A and singer E, singer B and singer H ", etc.) may be specified.
The way of singing is considered to reflect the personality and musical taste of the person. For example, an honest and shy person will sing in a stable and straight manner, and an open and passionate person is expressive. Also, the way of singing is completely different between those who listen only to classical music and those who listen only to enka. By collecting such features in advance, generating personality information and compatibility information and creating a database, personality / compatibility can be determined based on song analysis data. In other words, the personal information and compatibility information can be output by searching the database using the song analysis data as a search key. In this case, personality judgment and compatibility judgment are performed after multiple people sing in order, and if the result is memorized, by checking those results, who and who are compatible Can also be made. According to this, the game of generating a couple of similar things can also be played.

Or you may make it select the song analysis data which satisfy | fill a predetermined condition with respect to the acquired song analysis data. Specifically, for example, the song analysis data of each member of the singer unit is stored in the storage unit in the storage unit of the server device, and the CPU of the server device is stored in the acquired song analysis data and the storage unit. The obtained singing analysis data is compared to the singing feeling of which member of which unit. And CPU of a server apparatus selects the song analysis data similar to the other member of the determined unit from a song analysis database, and alert | reports to a user. In this way, for example, when the user has a feeling of singing similar to a member of a certain singer unit, it can be known that it is effective to sing that part.
You can also search for people who have singing voices with certain characteristics, or who resemble the singing feeling of a particular member of a unit. That is, such a request is registered in the server device 3, and the server device 3 adds a mark (flag or the like) indicating that the request has been made to the song analysis data stored in advance. When a song similar to this is input, the person who requested the identification information (or name data, etc.) is notified to that person. If the person who made the request has registered an e-mail address with the server, the e-mail address may be notified. In this way, a person with a desired singing feeling can be easily searched.

(2) In the first embodiment described above, information indicating the power, pitch, and spectrum of the voice is used as the song analysis data, but information indicating the pitch of the voice may be used as the song analysis data. Or you may make it use the information which shows a spectrum as song analysis data. In short, information indicating at least one of the pitch, spectrum, and power of voice may be used as song analysis data. In addition, the user may be allowed to select which information of pitch, spectrum, and power is to be used using the operation unit. Or you may enable it for a user to select either of the singing techniques shown in 2nd Embodiment.

Moreover, you may make it alert | report to a user the result which integrated | combined several information, such as a pitch, power, and a spectrum.
FIG. 8 is a diagram illustrating an example of a screen for informing a result of combining a plurality of pieces of information. In this example, the CPU 31 of the server device 3 calculates the search results of pitch, power, and spectrum as numerical values, performs weighting, and outputs a comprehensive result.

(3) The form of notification of the search result by the karaoke device is not limited to display, but may be a form that outputs a voice message, for example, or the message is sent to the user's mail terminal in the form of an e-mail. It may be in a form such as being transmitted to. In short, any notification form that can transmit a message or information to the user by any means is acceptable.

(4) In the above-described embodiment, the user indicated by the identification information corresponding to the selected song analysis data is notified. In addition to this, the identification corresponding to the selected song analysis data is provided. You may make it alert | report to the singer which information shows (henceforth "the selected singer") that it was selected.
Specifically, for example, the server device transmits information indicating that the server device has been selected to the karaoke device used by the selected singer, and the CPU of the karaoke device uses the received information as “ You may be able to display a message such as “XX's voice quality similar to you wants a virtual duet”. Alternatively, the message may be sent to the selected singer in the e-mail format. In this way, the selected singer can recognize that he has been selected. When transmitting to the singer selected in the e-mail format, the e-mail address of the person is stored in association with the identification information together with the singing analysis data, and is transmitted to the address. That's fine.
Note that the communication address that is the destination address of the message is not limited to the e-mail address, and may be the IP address or MAC address of the karaoke device used by the selected singer, or the selected singer. It may be the IP address or MAC address of the personal computer used by. Or the telephone number of a singer may be sufficient. In the case of a telephone number, the server apparatus or karaoke apparatus automatically calls the telephone number stored in association with the identification information, and reproduces the voice message stored in advance when the call connection is established. You may do it. In short, the communication address indicating the contact information of the singer is stored in association with the identification information, the communication address corresponding to the identification information is read out from the storage means, and the message indicating that the selection is made to the read communication address May be communicated.

Moreover, in a karaoke box etc., if song analysis data is produced | generated about the user of each room, it is easy to make the combination of the above virtual duets. In this case, if you have an ID for each karaoke device installed in each room, you can know from which room the singing voice is input, so people with similar singing voices are present The above-mentioned message such as “Mr. XX who has a voice quality similar to you wants a virtual duet” can be displayed on the monitor device in the room.
When responding to this, a virtual duet can be performed in real time by adding the sound input to the karaoke device to the sound input system of the karaoke device in the other party's room. The accompaniment may be configured so that the accompaniment signal in one of the rooms is transferred to the karaoke apparatus in the other room. Similarly, virtual chorus can be performed in three or more rooms.

(5) In the above-described embodiment, the song analysis data serving as the search key is generated by the CPU of the karaoke apparatus 2. Instead, the CPU 11 prompts the user to input song analysis data. And the user may input singing analysis data. In this case, for example, the CPU 11 displays a screen that prompts the user to input song analysis data on the display unit 15, and the user sends the song analysis data to the karaoke apparatus 2 via an interface such as a USB (Universal Serial Bus). Just input. In this case, the singing analysis data may be generated in advance by a device such as a personal computer. At this time, as in the above-described embodiment, the personal computer collects the voice of the singer with the microphone, analyzes the collected voice, and generates song analysis data.
Alternatively, the karaoke apparatus 2 may be provided with an RFID reader so that the RFID in which the singing analysis data is written is read by the RFID reader of the karaoke apparatus 2. In short, the singing analysis data may be acquired by the CPU 11 or may be input directly into the CPU 11.

  Alternatively, the song analysis data may be designated by inputting identification information. In this case, for example, the CPU 11 may display a screen that prompts the user to input identification information on the display unit 15, and the user may operate the operation unit 16 to input the karaoke device 2. In this case, when the CPU 11 of the karaoke apparatus 2 transmits the identification information to the server apparatus 3 and the CPU 31 of the server apparatus 3 receives the identification information, the singing analysis data corresponding thereto is read from the singing analysis database storage area 34a.

(6) In addition to the identification information for identifying the singer, the song identification information for identifying the song may be stored in the song analysis database in association with the song analysis data. In this way, when searching for song analysis data, if song identification information is also input, the search can be performed for a song analysis data group with matching song identification information. You can look for people with similar singing voices about your songs.

(7) In the above-described embodiment, the search system 1 in which the karaoke device 2 and the server device 3 are connected via a communication network realizes all the functions according to the present embodiment. On the other hand, three or more devices connected via a communication network may share the above functions, and a system including the plurality of devices may realize the system of the embodiment. Alternatively, one device may realize all of the above functions.

(8) Programs executed by the CPU 11 of the karaoke apparatus 2 or the CPU 31 of the server apparatus 3 in the above-described embodiment are a magnetic tape, a magnetic disk, a flexible disk, an optical recording medium, a magneto-optical recording medium, and a CD (Compact Disk)- It can be provided in a state stored in a recording medium such as a ROM, a DVD (Digital Versatile Disk), or a RAM. It is also possible to download to the karaoke apparatus 2 or the server apparatus 3 via a network such as the Internet.

It is a block diagram which shows an example of a structure of the search system which concerns on 1st Embodiment of this invention. It is a block diagram which shows an example of the hardware constitutions of the karaoke apparatus of the embodiment. It is a block diagram which shows an example of the hardware constitutions of the server apparatus of the embodiment. It is a figure which shows an example of the content of the song analysis database of the embodiment. It is a figure which shows an example of the screen displayed on the display part of the karaoke apparatus of the embodiment. It is a figure which shows an example of the content of the song analysis data which concerns on 2nd Embodiment of this invention. It is a figure for demonstrating the detection process of a false set. It is a figure which shows an example of the screen displayed on the display part of a karaoke apparatus.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Search system 2, 2a, 2b, 2c ... Karaoke apparatus, 3 ... Server apparatus, 4 ... Communication network, 11, 31 ... CPU, 12, 32 ... ROM, 13, 33 ... RAM, 14, 34 ... Memory | storage part , 15 ... display unit, 16 ... operation unit, 17 ... microphone, 18 ... audio processing unit, 19 ... speaker, 20, 35 ... communication unit.

Claims (7)

Storage means for storing a plurality of pairs of identification information for identifying a singer and singing analysis data indicating characteristics of the singing voice of the singer;
Acquisition means for acquiring singing analysis data indicating the characteristics of the singing voice of the singer;
The singing analysis data acquired by the acquisition unit and the singing analysis data stored in the storage unit are compared, and one or more singing analysis data is obtained from the singing analysis data stored in the storage unit according to the degree of coincidence. A selection means to select;
A search apparatus comprising: output means for reading identification information corresponding to the song analysis data selected by the selection means from the storage means and outputting the read identification information. The storage means stores singer information related to a singer in association with the identification information,
The output means reads the identification information corresponding to the singing analysis data selected by the selection means from the storage means, outputs the read identification information, and the singer information corresponding to the identification information from the storage means. The retrieval apparatus according to claim 1, wherein the retrieved singer information is notified. The storage means stores a communication address indicating a contact address of the singer in association with the identification information,
The output means reads identification information corresponding to the song analysis data selected by the selection means from the storage means, outputs the read identification information, and reads a communication address corresponding to the identification information from the storage means. 2. The search device according to claim 1, wherein a message indicating that the message is selected is communicated to the read communication address.   The search apparatus according to claim 1, wherein the singing analysis data is data indicating at least one of a pitch, a spectrum, and power of the voice.   The search apparatus according to claim 1, wherein the singing analysis data is technique data indicating a type and timing of a technique used for singing. Input means for outputting the voice of the input singer as voice data;
Generating means for generating the song analysis data from the voice data output by the input means,
The search device according to any one of claims 1 to 5, wherein the acquisition unit acquires song analysis data generated by the generation unit.   The search device according to claim 6, further comprising storage control means for storing the song analysis data generated by the generation means in the storage means.

Images